SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04673 · EMNLP · 2021

DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

Hannaneh Hajishirzi, Mari Ostendorf, Zeqiu Wu, Bo-Ru Lu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.04673")
get_code_for_paper("2109.04673")
have("2109.04673")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.04673.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.04673.svg)](https://syntology.ai/paper/2109.04673)

Connect an agent — have() is free.